Review & quality
19,471 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
ch040602/skill-vaccine/skills/skill-vaccine-review Skill
no license0★ repoScan-gated safety for Agent Skills before they reach Codex, Claude Code, CI, or a registry.
satishTheLegend/pro-se-dispute-resolver Skill
0★Self-advocacy for non-lawyers: from a wrong you suffered to a verified, deadline-aware paper trail, demand letter, and the right complaint forum.
jeftarmascarenhas/design.md Skill
0★A dependency-free, agent-agnostic skill to create, validate, preview & export DESIGN.md files — no CLI required.
baolinhtb/BMAD-Odoo-Skills/assets/skills/bmad-qa-visual-review Skill
0★ repoOne-command BMAD METHOD + Odoo dev environment for Claude Code (BA skill, Odoo subagents, agent overrides, Visual-QC)
pablonification/grok-build-consult-claude/skills/consult-claude Skill
0★ repoGrok Build skill: read-only second opinions from Claude Code (plan, review, advice)
hoangCreative/debug-external-first Skill
0★A debugging reflex for AI assistants: when a third-party tool breaks, search the community before guessing. The bug is usually external state that moved, not your code.
gawakawa/gh-skill/skills/commit Skill
no license0★ reponledford/engineering-review-board/skills/adversarial-review Skill
0★ repoA collection of AI agent skills I have written
host452b/polish/skills/before-git-push Skill
no license0★ repoClaude Code skill/plugin that rewrites a raw question into a high-performing LLM prompt by auto-selecting research-backed prompt-engineering strategies.
OctopusGarage/octopusgarage-skills/skills/octopusgarage-heat-guard Skill
no license0★ repo🧰 Practical agent skills for OctopusGarage workflows.
gvago/unofficial-qodo-review-skills/skills/apex-review Skill
0★ repoUnofficial agent skills for Qodo Merge PR review. Includes terraform-review (adapted from antonbabenko/terraform-skill).
cp3hnu/agent-skills/skills/next-formatting Skill
0★ repoAgent Skills for formatting and linting workflows in frontend projects
satejbidvai/skills/skills/post-pr-review Skill
no license0★ repoPR review as agent skills. My code-review standards, installable in any skills.sh agent.
JEJ111/the-forge/skills/forge Skill
0★ repoThe Forge - an unbounded recursive multi-agent methodology (diverge -> adversarial critique -> verify -> handoff -> repeat). Vendor-neutral spec + Claude Code skill, installable via skills.sh.
faber-craft/faber-resume/skills/faber-ats Skill
0★ repoAI resume crafting skill suite - anti-AI voice, per-bullet framework routing, ATS optimization
codeeater/where-to-plai-plugin/plugins/where-to-plai/skills/advisory-board Skill
0★ repoWhere-to-PlAI — Market Opportunity Navigator (Where to Play) as a Claude Code/Cowork plugin.
satishTheLegend/principal-architect-review Skill
0★Claude Code skill: a principal-engineer architecture review board — C4 model, ADRs, adversarial review, and evolutionary-architecture fitness functions wired into CI to catch drift.
abdalrahman-ahmed/agentflow-template/skills/agentflow Skill
0★ repoAgentFlow is a self-contained developer agent workflow framework and execution engine for Antigravity IDE (and compatible agents like Claude Code).
clankercode/pirfl Skill
no license0★Fallibilist Plan → Implement → Review → Fix → Loop skill for robust agent workflows
LevyBytes/AI-SKILL-github Skill
0★Agent Kaizen skill for Claude Code & Codex: faithful, task-routed GitHub reference, repositories, branch protection & rulesets, pull requests (merge/squash/rebase, CODEOWNERS), issues & Projects, GitHub Actions workflows (.github/workflows/\*.yml, GITHUB_TOKEN, matrix) and the gh CLI. Defers core git mechanics to the git skill.
TopScrech/rename-branch-skill Skill
no license0★draculavan/agent-skill-atlas/examples/demo-skills/code-review Skill
no license0★ repoA local-first visual atlas for your AI agent skills.
comment-hq/skills/skills/code-review Skill
0★ repoComment.io engineering-workflow skills for any AI coding agent (Claude Code, Codex, Cursor) — plan, prototype, build, review, ship. npx skills add comment-hq/skills
hztopcu/academic-research-skills-universal/ars_universal/assets/academic-paper-reviewer Skill
no license0★ repoUniversal cross-platform installer and adapter layer for Academic Research Skills across Codex, Claude Code, Cursor, VS Code, Aider, and other coding agents.
Sarmkadan/dotnet-senior-skills/skills/api-layer-boundaries Skill
0★ repoSenior-level .NET review rules for AI coding agents - Claude Code skills, Cursor rules, and Copilot instructions from one source
gadost/regitize/skills/regitize-authors Skill
0★ repoPortable AI-agent skills for auditing and improving Git history
AliceEinstein/copy-court Skill
0★A dowager editor who puts your copy on trial. An Agent Skill that catches formula, AI slop, borrowed brand voice, and hollow marketing copy before you publish.
linxumoney/ui-critique-coach/skills/ui-critique-coach Skill
0★ repo开源 AI UI/UX 评审 Skill：检查用户任务、信息层级、交互状态、响应式和可访问性。
keithhegit/sci-using-kit/skills/literature-review-search Skill
0★ repoA skill family for evidence-bounded SCI manuscript workflows: literature vetting, claim-evidence alignment, paper revision, reviewer preflight, LaTeX editing, and submission packaging.
1stIndeXR/deep-code-review-skill Skill
0★Evidence-driven, risk-ranked deep code review skill for Codex and Claude Code
Fatih0234/pi-caveman/skills/caveman-commit Skill
0★ repoDefault-off Caveman mode, companion skills, and Pi-native stats for Pi Coding Agent
XyraSinclair/canonicalize/skills/canonicalize Skill
0★ repoDrive artifacts to book-shape: precommitted denominator, machine-enforced truth, stranger-first surfaces, one-voice scrape, adversarial rounds until a round finds nothing. The applied art distilled from real canonicalization drives, with receipts.
bilals2008/bilal-skills/skills/commit-message-writer Skill
0★ repoAI agent skills collection for web systems and app development
yshmr/codex-goal-draft-policy/skill/goal-draft-policy Skill
0★ repoCodexの/goalを有効化する前に、レビュー可能なcompletion contractを作成・評価するSkill。失敗保存型の評価証拠、pure validation、bounded E2Eを収録（MIT）。
Thecsiz/tastemaker/skills/tastemaker Skill
no license0★ repoAI design-critique skill that teaches measurable craft and evaluates taste in context
runsagents/settlement-proof Skill
0★Uses transaction reconciliation to verify payment claims across the processor, ledger, idempotency records, and settlement data.
flopeztancredi/slopmd/skills/check-dep Skill
0★ repoThe markdown doctor for AI-written code. Diagnose, treat, and prevent AI slop with any coding agent.
junkim327/skills/skills/jira-ticket-workflow Skill
0★ repoPublic agent skills for Jira-backed development workflows
daanaagua/check-my-vibe-skill/skills/check-my-vibe Skill
0★ repoAgent Skill for authorized passive security scans of AI-built and vibe-coded websites
promptclickrun/purpose-check Skill
0★A judgment layer that helps AI agents build the right thing, ask fewer better questions, and preserve purpose through consequential work.
kaskilling/second-opinion/second-opinion Skill
0★ repoCodex skill for a fresh critical second-opinion review, fix, and re-review loop.
ribbons-digital/skills/blaze Skill
0★ repoSkills that design the work: a growing toolkit of disciplined, harness-agnostic processes for coding agents.
papukaijaorg/grill-docs Skill
0★Grill first, render last — an Agent Skill that refuses to make slides until purpose, audience, and issues are explicit. 資料を作る前に、あなたを炙るスキル。
marinsokol5/change-review/skills/change-review Skill
0★ repoThe human review step for AI-written changes: your agent proposes, you decide — inline diff in the browser, line comments, per-chunk apply, verdict back to the agent as JSON. Ships as an agent skill.
codalanguez/Monkii/skills/code-reviewer Skill
0★ repo🐒 Local, private LLM studio for Ollama — projects, Claude-style skills, and live file knowledge. Nothing leaves your machine.
scarlettdetekelala/motion-quality-gate/skills/motion-quality-gate Skill
0★ repoEvidence-first motion review skill for AI coding agents.
ohyesgocool/feature-loop/skills/address-review Skill
0★ repoLoop engineering for AI coding agents: plan → build → MR → independent AI review → fix → re-review until clean, with a merge gate and a self-learning blind-spot ledger. Agent Skills format, Claude Code native, MIT.
nuokunkeji/give-ai-a-spine/plugins/give-ai-a-spine/skills/reality-check Skill
0★ repoGive your AI a spine. Less agreement, more honest work.
HuangJingwang/change-crew/skills/change-crew Skill
0★ repoMulti-agent delivery workflow for Codex and SKILL.md-compatible coding agents
DeliriumPulse/codetruss-plugins/plugins/codetruss-claude/skills/codetruss Skill
0★ repoLocal acceptance gate for coding-agent changes — skills-only plugin for Claude Code and Codex
bkvito/dk-agent-skills/skills/clear-git-proxy Skill
0★ reporunsagents/second-opinion-bench Skill
0★Benchmarks LLM reviewers on a fault-seeded corpus: does a second opinion from a different model actually catch more, by defect class?
praneel95/skillguard/examples/safe-skill Skill
0★ repoStatic security scanner for AI agent skills and plugins — flags prompt injection, hidden Unicode, exfiltration, and dangerous commands in SKILL.md/CLAUDE.md and scripts.
trac3r00/agent-guards/skills/claim-audit Skill
0★ repoAgent Guards for long-lived AI agents: context-budget (audit per-turn token weight, fail CI on bloat) + claim-audit (flag unverified factual claims). Standalone tools + CI-ready, Claude Code / Codex / OpenCode compatible.
grimoire-rs/grimoire-vscode/.claude/skills/finalize Skill
0★ repoVS Code marketplace UI for grim — the OCI package manager for AI artifacts (skills, rules, agents, MCP servers, bundles).
connorjjarvis/interview-me/interview-me Skill
0★ repoTwo staff-level agent skills (Claude Code / Copilot CLI / Codex). interview-me-senior grills and scores your decisions; review-me-senior is a review copilot with auto-detected best-practice packs (C#/.NET, Blazor/Fluxor) that learns your conventions.
reindent/boards/skills/boards Skill
0★ repoThe project board that writes itself while you build.
linxumoney/earnings-signal-reviewer/skills/earnings-signal-reviewer Skill
0★ repo开源 AI 财报分析 Skill：审阅业绩预期差、盈利质量、现金流、管理层指引和研究论点变化。
DevOtts/review-it Skill
0★The QA front door of the DevOtts lifecycle family — plan-it plans, fable-it builds, review-it verifies. Runs the plan-phase Test Contract against the build and enforces an 11-rule gate catalog that makes false-VERIFIED claims un-shippable.
xingtaxueshu/literature-review-skills Skill
0★Five open agent skills for sharper literature reviews: question refinement, review modules, method comparison, contradiction mapping, and research gap discovery.